jailbreak defense

Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models AAAI 2026 EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering AAAI 2026 Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory CVPR 2026 MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting AAAI 2026 SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory ACL 2026 SafetyReminder: Reviving Delayed Safety Awareness of Vision-Language Models to Defend Against Jailbreak Attacks AAAI 2026 Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model ACML 2025 AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025 AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders EMNLP 2025 Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders EMNLP 2025 Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refine NAACL 2025 DeTAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification ACL 2025 How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation EMNLP 2025 Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update AAAI 2025 Multilingual Collaborative Defense for Large Language Models EMNLP 2025 MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025 Proxy Barrier: A Hidden Repeater Layer Defense Against System Prompt Leakage and Jailbreaking EMNLP 2025 Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking EMNLP 2025 Representation Bending for Large Language Model Safety ACL 2025 Robust LLM safeguarding via refusal feature adversarial training ICLR 2025 Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025 Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks CVPR 2025 Unraveling the Mystery: Defending Against Jailbreak Attacks Via Unearthing Real Intention COLING 2025